Skip to main content
placeholder image

A knowledge-based system for temperature prediction in hot strip mills

Conference Paper


Abstract


  • Rolling temperature is an important factor affecting mechanical properties of hot rolled strip significantly. Traditional techniques cannot meet higher precision control imperatives. In the present work, a novel knowledge-based system has been developed for the temperature prediction in hot strip mills. Neural network has been used for this purpose, which is an intelligent technique that can solve nonlinear problem of temperature control by learning from the samples. Furthermore, an annealing robust learning algorithm was presented to adjust the hidden node parameters as well as the weights of the adaptive neural networks. Simulations in a multi-object mode have been carried out to verify the effectivity of new neural optimization system. Calculation results confirm the feasibility of this approach and show a good agreement with experimental values obtained from a steel plant.

UOW Authors


  •   Jiang, Zhengyi (external author)
  •   Xie, Haibo

Publication Date


  • 2008

Citation


  • Xie, H. B., Jiang, Z. Y., Wei, D., Liu, X. H., & Wang, G. D. (2008). A knowledge-based system for temperature prediction in hot strip mills. In Advanced Materials Research Vol. 32 (pp. 153-156). doi:10.4028/0-87849-475-8.153

Scopus Eid


  • 2-s2.0-45749115769

Web Of Science Accession Number


Start Page


  • 153

End Page


  • 156

Volume


  • 32

Abstract


  • Rolling temperature is an important factor affecting mechanical properties of hot rolled strip significantly. Traditional techniques cannot meet higher precision control imperatives. In the present work, a novel knowledge-based system has been developed for the temperature prediction in hot strip mills. Neural network has been used for this purpose, which is an intelligent technique that can solve nonlinear problem of temperature control by learning from the samples. Furthermore, an annealing robust learning algorithm was presented to adjust the hidden node parameters as well as the weights of the adaptive neural networks. Simulations in a multi-object mode have been carried out to verify the effectivity of new neural optimization system. Calculation results confirm the feasibility of this approach and show a good agreement with experimental values obtained from a steel plant.

UOW Authors


  •   Jiang, Zhengyi (external author)
  •   Xie, Haibo

Publication Date


  • 2008

Citation


  • Xie, H. B., Jiang, Z. Y., Wei, D., Liu, X. H., & Wang, G. D. (2008). A knowledge-based system for temperature prediction in hot strip mills. In Advanced Materials Research Vol. 32 (pp. 153-156). doi:10.4028/0-87849-475-8.153

Scopus Eid


  • 2-s2.0-45749115769

Web Of Science Accession Number


Start Page


  • 153

End Page


  • 156

Volume


  • 32